Closed hnykda closed 9 years ago
Kotrfa, I'm not totally sure what you are asking for. In the example I have, I prime the network with a word embedding from the word "the". If you instead show your LSTM your input vector instead of a word embedding you will achieve what I think you wanted ?
Sorry for my ignorance - my knowledge about RNN isn't particularly good and hence my question. Now I understand.
Hello,
I have some sequence of vectors of the same length. Now I would like to train LSTM on train sample of this sequence and then make the network predict new sequence of vectors of the same length as input based on several priming vectors.
I cannot find easily applicable example anywhere on the internet and I thought that your code could be suitable. Couldn't you please edit your example with words or add some new, which would done what I'm looking for?
Thank you